> For the complete documentation index, see [llms.txt](https://docs.owkin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.owkin.com/collaborate-and-share/customize-k-pro.md). # Customize K-Pro K-Pro can be adapted to how your team works, at three levels: the **methods** it applies (skills), the **data and tools** it can reach, and the way you **organize and share** results. ### Skills: encode your methods Skills are how you run complete multi-step workflows in one go, and how your bioinformatics and biology teams capture internal best practice. A skill is written in natural language, so no coding is needed to read or adapt it. Customer-specific skills can capture, for example: * internal scoring methodologies and weighting preferences * naming conventions and preferred ontologies * report templates and output formats * the methodology of your internal experts or KOLs Skills are managed with the controls you'd expect for shared methodology: * **Create or import**: write a skill in the skill editor, or import an existing `SKILL.md` file, with supporting files if needed. * **Run on demand**: type `/` followed by the skill name in a prompt to run it explicitly. K-Pro can also pick a relevant skill on its own. * **Versioning**: every save creates a new version, and one version is set as active. You can go back to a previous version when you need to. * **Sharing**: a skill belongs to its author, who can share it with specific colleagues or with the whole organization, as a reader (can use it) or an editor (can change it). Ownership can be transferred when responsibilities change. * **Gallery**: browse the skills available to you, and filter them by tag or by author. See [Writing reproducible skills](/what-you-can-do-with-k-pro/writing-reproducible-skills.md) for how to write a good skill, and [On K-Pro skills](/governance-and-security/model-governance/explainability-and-traceability/on-k-pro-skills.md) for how skills drive scoring and prioritization. {% hint style="info" %} Skills are available per organization, on request. During onboarding, Owkin's team can help you translate existing methodologies into skills. Contact your Owkin representative to enable skills for your team. {% endhint %} ### Your data and tools * **Your own data**: proprietary datasets can be connected to K-Pro. Owkin registers them for your organization, for example from cloud storage or a data warehouse, or through an MCP server that wraps an internal database. See [Connecting your data sources](/integrate-your-data/connecting-your-data-sources.md). * **Your internal tools**: internal tools such as compound libraries, biomarker pipelines, or real-world data systems can be connected as MCP servers. Once connected, K-Pro's orchestrator can call them like any other tool, alongside Owkin's agents. * **Custom scoring dimensions**: an internal MCP server can add your own criteria to a prioritization, for example "also penalize targets that failed our internal toxicity screen". MCP servers are configured by Owkin for your organization's deployment, and access to each tool is controlled per organization. ### Organize and share your work * **Results that stay with the conversation**: plots, tables, and reports produced in a conversation stay attached to it, so you can come back to them later. * **Exports**: download plots as PNG or SVG (with a configurable size), and, where enabled, download reports as PDF and export clinical trial timelines to PowerPoint, ready to reuse in your own presentations and documents. * **Iterate on outputs**: filter, re-rank, and reformat results in follow-up prompts until they match your team's needs. See [Collaboration features](/collaborate-and-share/collaboration-features.md) for how teams work together in K-Pro. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.owkin.com/collaborate-and-share/customize-k-pro.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.